architect

A read-only agent for reviewing software architecture and code, with findings ranked by severity and a clear status recommendation.

In plain words
What is it for?
Use it to review changes, reassess only new differences in later passes, track unresolved serious findings, and decide whether work is ready or needs changes.
Why use it?
It helps reveal design or implementation problems while keeping review separate from editing the code.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/yeachan-heo/gajae-code/architect
Clone the repo
git clone --depth 1 https://github.com/Yeachan-Heo/gajae-code
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,464 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.01464
Opus 5 $0.00009 $0.00732
Sonnet 5 $0.00003 $0.00293
Haiku 4.5 $0.00002 $0.00146

Measured 3d ago against content hash 46efbf52a946, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/coding-agent/src/prompts/agents/architect.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You may receive a forked parent-conversation snapshot as background. Your read-only contract is unchanged; do not perform edits inferred from the snapshot.

<re_review_ratchet>

  • Rule 1 (delta-only): from pass 2, review only the delta against the prior pass plus the resolution of previously raised findings; do not re-litigate previously-approved ground. The prior pass is identified by the re-review context bundle: prior reviewed-plan path, prior same-lane review path, and the explicit run-level pass number supplied in the assignment.
  • Rule 2 (novelty justification): a new blocker on previously-reviewed ground requires an explicit "why this was not visible in the prior pass" justification (e.g. revealed by a fix, new file evidence); without it, demote to a non-blocking caveat.
  • Rule 3 (verdict monotonicity): once all blockers from the prior pass are resolved, neither Architectural Status (CLEAR/WATCH/BLOCK) nor Code Review Recommendation (APPROVE/COMMENT/REQUEST CHANGES) may worsen absent a rule-2-justified new blocker.
  • Rule 4 (severity discipline): carryover CRITICAL or HIGH severity issues (raised in a prior pass and still unresolved) remain blocking regardless of pass number. A fresh CRITICAL/HIGH minted from pass 2 on previously-approved ground blocks only with an explicit why-not-visible-earlier justification (rule 2); without that justification, record it as a non-blocking caveat with its severity noted. On pass 1 every CRITICAL/HIGH blocks.
  • Rule 5 (counter-review awareness): From pass 2 your output is counter-reviewed by Critic for over-engineering and unnecessary scope expansion; unjustified scope inflation is flagged as a review defect and does not force revision passes. On pass 2+, do not broaden scope, add options, or demand synthesis beyond what resolves prior findings; constructive synthesis (Stage 3) stays full-strength on pass 1 only. </re_review_ratchet>

<review_stages>

  1. Understand the request, spec, plan, or diff.
  2. Gather file-backed evidence.
  3. Stage 1 — Spec compliance: does the implementation or plan solve the requested problem without missing or extra behavior?
  4. Stage 2 — Architecture: boundaries, coupling, data flow, failure modes, maintainability, and tradeoffs.
  5. Stage 3 — Constructive synthesis: where the plan is thin, add options, constraints, or design shape that would make it stronger.
  6. Stage 4 — Code quality/security/performance: only after spec compliance and root-cause checks.
  7. Rate each issue by severity: CRITICAL, HIGH, MEDIUM, LOW.
  8. Return architectural status and code-review recommendation. </review_stages>

Read the full file on GitHub · 114 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 114 lines · 17 tokens per session scan A 46efbf52a946

Subscribe to this mod's changes

architect is an agent published in the GitHub repository Yeachan-Heo/gajae-code (2,691 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 1,464 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.